@inproceedings{yang-katiyar-2020-simple,
title = "Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning",
author = "Yang, Yi and
Katiyar, Arzoo",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.516",
doi = "10.18653/v1/2020.emnlp-main.516",
pages = "6365--6375",
abstract = "We present a simple few-shot named entity recognition (NER) system based on nearest neighbor learning and structured inference. Our system uses a supervised NER model trained on the source domain, as a feature extractor. Across several test domains, we show that a nearest neighbor classifier in this feature-space is far more effective than the standard meta-learning approaches. We further propose a cheap but effective method to capture the label dependencies between entity tags without expensive CRF training. We show that our method of combining structured decoding with nearest neighbor learning achieves state-of-the-art performance on standard few-shot NER evaluation tasks, improving F1 scores by 6{\%} to 16{\%} absolute points over prior meta-learning based systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-katiyar-2020-simple">
<titleInfo>
<title>Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arzoo</namePart>
<namePart type="family">Katiyar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a simple few-shot named entity recognition (NER) system based on nearest neighbor learning and structured inference. Our system uses a supervised NER model trained on the source domain, as a feature extractor. Across several test domains, we show that a nearest neighbor classifier in this feature-space is far more effective than the standard meta-learning approaches. We further propose a cheap but effective method to capture the label dependencies between entity tags without expensive CRF training. We show that our method of combining structured decoding with nearest neighbor learning achieves state-of-the-art performance on standard few-shot NER evaluation tasks, improving F1 scores by 6% to 16% absolute points over prior meta-learning based systems.</abstract>
<identifier type="citekey">yang-katiyar-2020-simple</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.516</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.516</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>6365</start>
<end>6375</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning
%A Yang, Yi
%A Katiyar, Arzoo
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F yang-katiyar-2020-simple
%X We present a simple few-shot named entity recognition (NER) system based on nearest neighbor learning and structured inference. Our system uses a supervised NER model trained on the source domain, as a feature extractor. Across several test domains, we show that a nearest neighbor classifier in this feature-space is far more effective than the standard meta-learning approaches. We further propose a cheap but effective method to capture the label dependencies between entity tags without expensive CRF training. We show that our method of combining structured decoding with nearest neighbor learning achieves state-of-the-art performance on standard few-shot NER evaluation tasks, improving F1 scores by 6% to 16% absolute points over prior meta-learning based systems.
%R 10.18653/v1/2020.emnlp-main.516
%U https://aclanthology.org/2020.emnlp-main.516
%U https://doi.org/10.18653/v1/2020.emnlp-main.516
%P 6365-6375
Markdown (Informal)
[Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning](https://aclanthology.org/2020.emnlp-main.516) (Yang & Katiyar, EMNLP 2020)
ACL